lindy-debug-bundle
Comprehensive debugging toolkit for Lindy AI agents. Use when investigating complex issues, collecting diagnostics, or preparing support tickets. Trigger with phrases like "lindy debug", "lindy diagnostics", "lindy support bundle", "investigate lindy issue".
- License 许可
- MIT
- 最近更新
- 2026-11-12
- Stars
- ★ 2.0k
- Forks
- 231
01 前言 Front Matter
- name
- lindy-debug-bundle
- author
- Jeremy Longshore <jeremy@intentsolutions.io>
- license
- MIT
- version
- 1.0.0
- description
- Comprehensive debugging toolkit for Lindy AI agents. Use when investigating complex issues, collecting diagnostics, or preparing support tickets. Trigger with phrases like "lindy debug", "lindy diagnostics", "lindy support bundle", "investigate lindy issue".
- allowed-tools
- Read, Write, Edit, Bash(curl:*), Grep
03 SKILL.md 正文
Lindy Debug Bundle
Overview
Comprehensive debugging toolkit for collecting diagnostics and resolving issues.
Prerequisites
- Lindy SDK installed
- Access to logs
- curl installed for API testing
Instructions
Step 1: Collect Environment Info
#!/bin/bash
echo "=== Lindy Debug Bundle ==="
echo "Date: $(date -u +%Y-%m-%dT%H:%M:%SZ)"
echo "Node: $(node -v)"
echo "npm: $(npm -v)"
echo ""
echo "=== SDK Version ==="
npm list @lindy-ai/sdk 2>/dev/null || echo "SDK not found"
echo ""
echo "=== Environment ==="
echo "LINDY_API_KEY: ${LINDY_API_KEY:+[SET]}"
echo "LINDY_ENVIRONMENT: ${LINDY_ENVIRONMENT:-[NOT SET]}"
echo ""
Step 2: Test API Connectivity
echo "=== API Connectivity ==="
curl -s -o /dev/null -w "Status: %{http_code}\nTime: %{time_total}s\n" \
-H "Authorization: Bearer $LINDY_API_KEY" \
https://api.lindy.ai/v1/users/me
echo ""
Step 3: Collect Agent State
// debug/collect-agent-state.ts
import { Lindy } from '@lindy-ai/sdk';
async function collectAgentState(agentId: string) {
const lindy = new Lindy({ apiKey: process.env.LINDY_API_KEY });
const bundle = {
timestamp: new Date().toISOString(),
agent: await lindy.agents.get(agentId),
runs: await lindy.runs.list({ agentId, limit: 10 }),
automations: await lindy.automations.list({ agentId }),
};
return bundle;
}
// Export for support
const state = await collectAgentState(process.argv[2]);
console.log(JSON.stringify(state, null, 2));
Step 4: Check Run History
async function analyzeRuns(agentId: string) {
const lindy = new Lindy({ apiKey: process.env.LINDY_API_KEY });
const runs = await lindy.runs.list({ agentId, limit: 50 });
const analysis = {
total: runs.length,
successful: runs.filter(r => r.status === 'completed').length,
failed: runs.filter(r => r.status === 'failed').length,
avgDuration: runs.reduce((a, r) => a + r.duration, 0) / runs.length,
recentErrors: runs
.filter(r => r.status === 'failed')
.slice(0, 5)
.map(r => ({ id: r.id, error: r.error })),
};
return analysis;
}
Step 5: Generate Support Bundle
async function generateSupportBundle(agentId: string) {
const bundle = {
generated: new Date().toISOString(),
environment: {
node: process.version,
platform: process.platform,
sdk: require('@lindy-ai/sdk/package.json').version,
},
agent: await collectAgentState(agentId),
analysis: await analyzeRuns(agentId),
};
const filename = `lindy-debug-${Date.now()}.json`;
fs.writeFileSync(filename, JSON.stringify(bundle, null, 2));
console.log(`Bundle saved to: ${filename}`);
return filename;
}
Output
- Environment diagnostic information
- API connectivity test results
- Agent state and configuration
- Run history analysis
- Exportable support bundle
Error Handling
| Issue | Diagnostic | Resolution |
|---|---|---|
| Auth fails | Check API key | Regenerate key |
| Timeout | Check network | Verify firewall |
| Agent missing | Check environment | Verify agent ID |
Examples
Quick Health Check
# One-liner health check
curl -s -H "Authorization: Bearer $LINDY_API_KEY" \
https://api.lindy.ai/v1/users/me | jq '.email'
Full Debug Script
#!/bin/bash
# save as lindy-debug.sh
echo "Collecting Lindy debug info..."
npx ts-node debug/collect-agent-state.ts $1 > debug-bundle.json
echo "Bundle saved to debug-bundle.json"
Resources
Next Steps
Proceed to lindy-rate-limits for rate limit management.
04 同仓库更多 Skills
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
neuropixels-analysis
Neuropixels neural recording analysis. Load SpikeGLX/OpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen/IBL curation, AI-assisted visual analysis, for Neuropixels 1.0/2.0 extracellular electrophysiology. Use when working with neural recordings, spike sorting, extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
notebooklm
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.
slack-gif-creator
Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."